Codesota · Models · trurl-2-7bVoicelab12 results · 1 benchmarks
Model card

trurl-2-7b.

Voicelabopen-source
§ 02 · Benchmarks

Every benchmark trurl-2-7b has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpoleval2018-task31098.88#21/56source ↗
02Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generaleq-bench22.6%#174/299source ↗
03Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpoquad-open-book54.8%#239/337source ↗
04Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalklej-ner-mc38.1%#299/490source ↗
05Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generaldyk42.7%#303/489source ↗
06Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalklej-ner-generative38.4%#308/489source ↗
07Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpolqa-open-book77.2%#335/489source ↗
08Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalaverage26.9%#378/491source ↗
09Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalppc51.9%#394/490source ↗
10Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalpolemo2-in67.7%#396/490source ↗
11Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalcbd16.5%#401/490source ↗
12Open PL LLM LeaderboardNatural Language Processing · Polish LLM Generalbelebele47.0%#424/490source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area

Where trurl-2-7b actually performs.

Natural Language Processing
1
benchmark
avg rank #306.0
§ 05 · Related models

Other Voicelab models scored on Codesota.

Voicelab/trurl-2-13b-academic
13B params · 0 results
§ 06 · Sources & freshness

Where these numbers come from.

speakleash/open_pl_llm_leaderboard
12
results
12 of 12 rows marked verified.